Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5353
    Prev
    Next
    INDEX
    Explanations

    phrases related to high-quality dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elf
    -0.07
    ante
    -0.07
    lan
    -0.07
    ovi
    -0.07
    so
    -0.07
    ORMAT
    -0.07
    sov
    -0.06
    лан
    -0.06
    978
    -0.06
    chen
    -0.06
    POSITIVE LOGITS
    ?url
    0.07
     ترÛĮÙĨ
    0.06
    æ
    0.06
    -grade
    0.06
    -forward
    0.06
    ê¸ī
    0.06
     dining
    0.06
    fare
    0.06
    WARD
    0.06
     lighting
    0.06
    Activations Density 0.008%

    No Known Activations